A Review of Soft Computing Approach for the Speed Estimation of Electric Drive
Pages : 1008-1009Download PDF
This paper describes a novel method of speed estimation in the field of automation and control of electrical drives based on artificial intelligence (AI). The artificial neural network (ANNs) models are composed of many non-linear computational elements operating in parallel and arranged in patterns similar to biological neural nets. This paper details a proposed scheme to identify the use of neural network model for the estimation of the speed of the rotating shaft driven by voltage controlled induction motor drive. In most of the process control applications the speed identification is based on the conventional analog type of electro-mechanical sensors like tachometer, optical pyrometer etc. These sensors require dynamics of the plant being controlled and are at risk of life due to the high-speed continuous motion of the shaft. Moreover, the conventional adaptive control schemes are complicated and need excessive computational effort for real time implementation. The paper proposes the highly parallel building blocks that illustrate neural net components and design principles used to track the systems like-speed estimation of induction motor drive. It details about the preferable use of contact less type of ANN model based sensors over the conventional one. The verification of the proposed work through physical experimentation definitely suggests the use of neural networks to solve the above problems by mimicking the adaptive control architecture in human brain.
Keywords: Artificial Neural Network (ANN), Estimator, Back-propagation algorithm, Induction motor, Adaptive control